摘要
从经济、社会、科技、环境、资源 5个方面对炼油企业可持续发展水平进行了综合评价 ,建立了评价指标体系。针对指标体系中各种指标由于度量单位不同而无法进行直接比较的问题 ,采用效用函数法对各项指标进行了无量纲处理。用层次分析法确定了指标的权重 ,通过求解最大特征根及其对应的特征向量 ,确定了表达每一层次元素相对重要性的权值 ,进而导出对整个问题的分析。利用B P神经网络分析法建立了网络评价模型 ,并采用实际数据样本对网络进行了训练和检验 。
The sustainable development level of oil-refining enterprises in five aspects of economy, society, science and technology, environment and resource was synthetically appraised, and an appraisement index system was established. The dimensionless handling for various indexes was made with effectiveness function. The weight values of indexes were determined with the analytical hierarchy process (AHP) method. By extracting the biggest feature root and its corresponding feature vector, the value of weight which expresses the element relative importance of each layer was determined. And then the analysis of the entire problem can be derived. A network appraisement model was established with BP neural network analysis method. The network was trained and inspected by the use of actual data samples. The result basically coincides with the actual appraisement value.
出处
《石油大学学报（自然科学版）》
CSCD
北大核心
2003年第6期121-124,130,共5页
Journal of the University of Petroleum,China(Edition of Natural Science)
基金
国家科技攻关项目 ( 2 0 0 2BA3 12B -0 8)
关键词
中国
炼油企业
可持续发展
评价模型
层次分析法
BP神经网络
oil-refining enterprise
sustainable development
analytical hierarchy process
B-P neural network
appraisement model
